ppAt Kyndryl, we run and reimagine the mission‑critical technology systems that drive advantage for the world’s leading businesses. We are at the heart of progress; we use proven expertise and a continuous flow of AI‑powered insight to enable smarter decisions, faster innovation, and a lasting competitive edge. /p h3The Role /h3 h3What You Will Do /h3 ul liDesign and build the agent harness: runtime, orchestration, tool and MCP integration, context and memory, evaluation, guardrails and observability. /li liBuild golden paths and reusable patterns so teams ship agents that are reliable, governed and measurable, instead of one‑off scripts. /li liDefine the oversight model: policy‑as‑code, human‑in‑the‑loop checkpoints, loop and failure detection, evaluation harnesses, and cost control. /li liIntegrate agents with the systems they act on: CI/CD, infrastructure, cloud services, observability and ticketing, through APIs and MCP. /li liMake agentic productivity measurable: define what productive means for each use case, instrument it, and run the harness on that data. /li liKeep the harness model‑agnostic and versioned, so it survives model upgrades and provider changes without rewrites. /li liMentor teams, run enablement, and reduce friction between Dev, Ops, Security and the people adopting agents. /li /ul h3What Success Looks Like In Your First Year /h3 ul liTeams ship agents through the harness golden paths instead of bespoke scripts. /li liAgentic workflows run in production with guardrails,



evaluation and measured productivity impact. /li liThe harness absorbs at least one model or provider upgrade without a rewrite. /li /ul h3Who You Are /h3 h3What you will bring /h3 ul li5+ years in Platform Engineering, DevOps or SRE, building developer platforms or runtime and orchestration systems in production. /li liHands‑on experience building agent harnesses or agentic systems: runtime, tool and MCP integration, orchestration, evaluation and guardrails. /li liSolid software engineering, primarily in Python, with the depth to build production systems and abstractions, not only prompts. /li liStrong cloud‑native background: Kubernetes, containers, Infrastructure as Code, and one major cloud (AWS, Azure or GCP). /li liA working grasp of how LLM agents fail and the engineering that makes them reliable: context design, loop and failure detection, verification and evaluation. /li liExperience treating a platform as a product: contracts, SLOs, adoption metrics and real users. /li liProfessional working English and Spanish. /li /ul h3Nice to have /h3 ul liAgent frameworks such as LangGraph, CrewAI, AutoGen etc. and the Model Context Protocol. /li liSerious production use of AI‑assisted development tools (Claude Code, Copilot, Codex). /li liLLMOps, agent evaluation, or observability for agentic systems. /li liPrior work on harnesses that stay stable across model upgrades. /li liPlatform engineering in regulated environments (finance, insurance, public sector). /li /ul /p #J-18808-Ljbffr

📌 Senior Platform Engineer – Agentic AI & Harness Engineering (Madrid)
🏢 Kyndryl
📍 Madrid